# Malware Similarity Search on EMBERSim (Benign)

Source: [Malware Similarity Search on EMBERSim (Benign)](<https://www.sota2.com/research/sota/malware-similarity-search-on-embersim-benign>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:51:46.074Z

Evaluation of model performance on malware similarity search using the EMBERSim (Benign) dataset, typically measured by mean Average Precision (mAP).

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Malware Similarity Search |
| Dataset (including any stated split) | EMBERSim (Benign) |
| Metric | Mean AP |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 26 of 26 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Mean AP](<https://www.sota2.com/research/sota/malware-similarity-search-on-embersim-benign.md?metric=Mean%20AP>): Higher is better; unit: PERCENT.

- [mAP](<https://www.sota2.com/research/sota/malware-similarity-search-on-embersim-benign.md?metric=mAP>): Higher is better; unit: PERCENT.

- [Standard Deviation](<https://www.sota2.com/research/sota/malware-similarity-search-on-embersim-benign.md?metric=Standard%20Deviation>): Lower is better; unit: SCALAR.

- [1% Percentile Score](<https://www.sota2.com/research/sota/malware-similarity-search-on-embersim-benign.md?metric=1%25%20Percentile%20Score>): Higher is better; unit: PERCENT.

- [10% Percentile Score](<https://www.sota2.com/research/sota/malware-similarity-search-on-embersim-benign.md?metric=10%25%20Percentile%20Score>): Higher is better; unit: PERCENT.

- [Median Score](<https://www.sota2.com/research/sota/malware-similarity-search-on-embersim-benign.md?metric=Median%20Score>): Higher is better; unit: PERCENT.

- [95% Percentile Score](<https://www.sota2.com/research/sota/malware-similarity-search-on-embersim-benign.md?metric=95%25%20Percentile%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Mean AP | Result date | Report paper |
| --- | --- | --- | --- |
| tag ranking algorithm | 99.6 | Not recorded | 68fa70b91e209131cea4cd58 |
| tag ranking algorithm | 99.6 | Not recorded | 68fa70b91e209131cea4cd58 |
| tag ranking algorithm | 99.6 | Not recorded | 68fa70b91e209131cea4cd58 |
| tag ranking algorithm | 98.6 | Not recorded | 68fa70b91e209131cea4cd58 |
| tag ranking algorithm | 98.6 | Not recorded | 68fa70b91e209131cea4cd58 |
| tag ranking algorithm | 98.6 | Not recorded | 68fa70b91e209131cea4cd58 |
| tag ranking algorithm | 97.5 | Not recorded | 68fa70b91e209131cea4cd58 |
| tag ranking algorithm | 97.5 | Not recorded | 68fa70b91e209131cea4cd58 |
| tag ranking algorithm | 97.5 | Not recorded | 68fa70b91e209131cea4cd58 |
| tag ranking algorithm | 96.7 | Not recorded | 68fa70b91e209131cea4cd58 |
| tag ranking algorithm | 96.7 | Not recorded | 68fa70b91e209131cea4cd58 |
| tag ranking algorithm | 96.7 | Not recorded | 68fa70b91e209131cea4cd58 |
| tag ranking algorithm | 95.1 | Not recorded | 68fa70b91e209131cea4cd58 |
| tag ranking algorithm | 95.1 | Not recorded | 68fa70b91e209131cea4cd58 |
| tag ranking algorithm | 95.1 | Not recorded | 68fa70b91e209131cea4cd58 |
| tag ranking algorithm | 93.3 | Not recorded | 68fa70b91e209131cea4cd58 |
| tag ranking algorithm | 93.3 | Not recorded | 68fa70b91e209131cea4cd58 |
| tag ranking algorithm | 93.3 | Not recorded | 68fa70b91e209131cea4cd58 |

### tag ranking algorithm

Mean AP: 99.6. Result ID: 699155cd3a6c31484907671c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Implementation](<https://github.com/CrowdStrike/embersim-databank>)

Recorded evaluation configuration: {"Scenario":"Counterfactual Analysis","Relevance Criterion":"EM","Top-K":1,"Co-occurrence Threshold":0.9}. This record does not assert independent reproduction.

### tag ranking algorithm

Mean AP: 99.6. Result ID: 699155cd3a6c31484907671f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Implementation](<https://github.com/CrowdStrike/embersim-databank>)

Recorded evaluation configuration: {"Scenario":"Counterfactual Analysis","Relevance Criterion":"IoU","Top-K":1,"Co-occurrence Threshold":0.9}. This record does not assert independent reproduction.

### tag ranking algorithm

Mean AP: 99.6. Result ID: 699155cd3a6c314849076722.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Implementation](<https://github.com/CrowdStrike/embersim-databank>)

Recorded evaluation configuration: {"Scenario":"Counterfactual Analysis","Relevance Criterion":"NES","Top-K":1,"Co-occurrence Threshold":0.9}. This record does not assert independent reproduction.

### tag ranking algorithm

Mean AP: 98.6. Result ID: 699155cd3a6c314849076713.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Implementation](<https://github.com/CrowdStrike/embersim-databank>)

Recorded evaluation configuration: {"Scenario":"Unsupervised Labelling","Relevance Criterion":"EM","Top-K":1,"Co-occurrence Threshold":0.9}. This record does not assert independent reproduction.

### tag ranking algorithm

Mean AP: 98.6. Result ID: 699155cd3a6c314849076716.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Implementation](<https://github.com/CrowdStrike/embersim-databank>)

Recorded evaluation configuration: {"Scenario":"Unsupervised Labelling","Relevance Criterion":"IoU","Top-K":1,"Co-occurrence Threshold":0.9}. This record does not assert independent reproduction.

### tag ranking algorithm

Mean AP: 98.6. Result ID: 699155cd3a6c314849076719.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Implementation](<https://github.com/CrowdStrike/embersim-databank>)

Recorded evaluation configuration: {"Scenario":"Unsupervised Labelling","Relevance Criterion":"NES","Top-K":1,"Co-occurrence Threshold":0.9}. This record does not assert independent reproduction.

### tag ranking algorithm

Mean AP: 97.5. Result ID: 699155cd3a6c314849076714.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Implementation](<https://github.com/CrowdStrike/embersim-databank>)

Recorded evaluation configuration: {"Scenario":"Unsupervised Labelling","Relevance Criterion":"EM","Top-K":10,"Co-occurrence Threshold":0.9}. This record does not assert independent reproduction.

### tag ranking algorithm

Mean AP: 97.5. Result ID: 699155cd3a6c314849076717.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Implementation](<https://github.com/CrowdStrike/embersim-databank>)

Recorded evaluation configuration: {"Scenario":"Unsupervised Labelling","Relevance Criterion":"IoU","Top-K":10,"Co-occurrence Threshold":0.9}. This record does not assert independent reproduction.

### tag ranking algorithm

Mean AP: 97.5. Result ID: 699155cd3a6c31484907671a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Implementation](<https://github.com/CrowdStrike/embersim-databank>)

Recorded evaluation configuration: {"Scenario":"Unsupervised Labelling","Relevance Criterion":"NES","Top-K":10,"Co-occurrence Threshold":0.9}. This record does not assert independent reproduction.

### tag ranking algorithm

Mean AP: 96.7. Result ID: 699155cd3a6c31484907671d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Implementation](<https://github.com/CrowdStrike/embersim-databank>)

Recorded evaluation configuration: {"Scenario":"Counterfactual Analysis","Relevance Criterion":"EM","Top-K":10,"Co-occurrence Threshold":0.9}. This record does not assert independent reproduction.

### tag ranking algorithm

Mean AP: 96.7. Result ID: 699155cd3a6c314849076720.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Implementation](<https://github.com/CrowdStrike/embersim-databank>)

Recorded evaluation configuration: {"Scenario":"Counterfactual Analysis","Relevance Criterion":"IoU","Top-K":10,"Co-occurrence Threshold":0.9}. This record does not assert independent reproduction.

### tag ranking algorithm

Mean AP: 96.7. Result ID: 699155cd3a6c314849076723.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Implementation](<https://github.com/CrowdStrike/embersim-databank>)

Recorded evaluation configuration: {"Scenario":"Counterfactual Analysis","Relevance Criterion":"NES","Top-K":10,"Co-occurrence Threshold":0.9}. This record does not assert independent reproduction.

### tag ranking algorithm

Mean AP: 95.1. Result ID: 699155cd3a6c314849076715.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Implementation](<https://github.com/CrowdStrike/embersim-databank>)

Recorded evaluation configuration: {"Scenario":"Unsupervised Labelling","Relevance Criterion":"EM","Top-K":100,"Co-occurrence Threshold":0.9}. This record does not assert independent reproduction.

### tag ranking algorithm

Mean AP: 95.1. Result ID: 699155cd3a6c314849076718.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Implementation](<https://github.com/CrowdStrike/embersim-databank>)

Recorded evaluation configuration: {"Scenario":"Unsupervised Labelling","Relevance Criterion":"IoU","Top-K":100,"Co-occurrence Threshold":0.9}. This record does not assert independent reproduction.

### tag ranking algorithm

Mean AP: 95.1. Result ID: 699155cd3a6c31484907671b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Implementation](<https://github.com/CrowdStrike/embersim-databank>)

Recorded evaluation configuration: {"Scenario":"Unsupervised Labelling","Relevance Criterion":"NES","Top-K":100,"Co-occurrence Threshold":0.9}. This record does not assert independent reproduction.

### tag ranking algorithm

Mean AP: 93.3. Result ID: 699155cd3a6c31484907671e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Implementation](<https://github.com/CrowdStrike/embersim-databank>)

Recorded evaluation configuration: {"Scenario":"Counterfactual Analysis","Relevance Criterion":"EM","Top-K":100,"Co-occurrence Threshold":0.9}. This record does not assert independent reproduction.

### tag ranking algorithm

Mean AP: 93.3. Result ID: 699155cd3a6c314849076721.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Implementation](<https://github.com/CrowdStrike/embersim-databank>)

Recorded evaluation configuration: {"Scenario":"Counterfactual Analysis","Relevance Criterion":"IoU","Top-K":100,"Co-occurrence Threshold":0.9}. This record does not assert independent reproduction.

### tag ranking algorithm

Mean AP: 93.3. Result ID: 699155cd3a6c314849076724.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Implementation](<https://github.com/CrowdStrike/embersim-databank>)

Recorded evaluation configuration: {"Scenario":"Counterfactual Analysis","Relevance Criterion":"NES","Top-K":100,"Co-occurrence Threshold":0.9}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.